{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 198,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 4.860405445098877,
      "learning_rate": 2e-05,
      "loss": 2.4586,
      "step": 1
    },
    {
      "epoch": 0.005050505050505051,
      "eval_loss": 0.9137344360351562,
      "eval_runtime": 3.5046,
      "eval_samples_per_second": 23.968,
      "eval_steps_per_second": 11.984,
      "step": 1
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 3.963740825653076,
      "learning_rate": 4e-05,
      "loss": 2.8025,
      "step": 2
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 3.753591299057007,
      "learning_rate": 6e-05,
      "loss": 2.2711,
      "step": 3
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 3.3850717544555664,
      "learning_rate": 8e-05,
      "loss": 1.9201,
      "step": 4
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 7.626316547393799,
      "learning_rate": 0.0001,
      "loss": 3.0043,
      "step": 5
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 89.29713439941406,
      "learning_rate": 0.00012,
      "loss": 2.3338,
      "step": 6
    },
    {
      "epoch": 0.03535353535353535,
      "grad_norm": 5.779690742492676,
      "learning_rate": 0.00014,
      "loss": 2.4511,
      "step": 7
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 19.235950469970703,
      "learning_rate": 0.00016,
      "loss": 1.7184,
      "step": 8
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 5.623316764831543,
      "learning_rate": 0.00018,
      "loss": 1.7096,
      "step": 9
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 7.677976131439209,
      "learning_rate": 0.0002,
      "loss": 1.4806,
      "step": 10
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 6.487170219421387,
      "learning_rate": 0.00019998603811858571,
      "loss": 1.6011,
      "step": 11
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 5.539438247680664,
      "learning_rate": 0.00019994415637302547,
      "loss": 1.0842,
      "step": 12
    },
    {
      "epoch": 0.06565656565656566,
      "grad_norm": 6.286291122436523,
      "learning_rate": 0.0001998743664582786,
      "loss": 1.1802,
      "step": 13
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 6.904139518737793,
      "learning_rate": 0.00019977668786231534,
      "loss": 1.1292,
      "step": 14
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 5.152040004730225,
      "learning_rate": 0.00019965114786067516,
      "loss": 0.9802,
      "step": 15
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 5.720455646514893,
      "learning_rate": 0.00019949778150885042,
      "loss": 1.0321,
      "step": 16
    },
    {
      "epoch": 0.08585858585858586,
      "grad_norm": 6.291650772094727,
      "learning_rate": 0.00019931663163249742,
      "loss": 0.9201,
      "step": 17
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 7.411867141723633,
      "learning_rate": 0.000199107748815478,
      "loss": 0.8879,
      "step": 18
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 11.839096069335938,
      "learning_rate": 0.0001988711913857346,
      "loss": 0.745,
      "step": 19
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 6.295371055603027,
      "learning_rate": 0.00019860702539900287,
      "loss": 1.0892,
      "step": 20
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 4.429136753082275,
      "learning_rate": 0.00019831532462036636,
      "loss": 0.8265,
      "step": 21
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 4.763950824737549,
      "learning_rate": 0.0001979961705036587,
      "loss": 0.7817,
      "step": 22
    },
    {
      "epoch": 0.11616161616161616,
      "grad_norm": 4.338098526000977,
      "learning_rate": 0.00019764965216871846,
      "loss": 0.7327,
      "step": 23
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 5.72149133682251,
      "learning_rate": 0.00019727586637650373,
      "loss": 0.8359,
      "step": 24
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 5.864504337310791,
      "learning_rate": 0.00019687491750207254,
      "loss": 0.8971,
      "step": 25
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 3.7987208366394043,
      "learning_rate": 0.00019644691750543767,
      "loss": 0.6958,
      "step": 26
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 8.180660247802734,
      "learning_rate": 0.0001959919859003031,
      "loss": 0.9494,
      "step": 27
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 9.300004005432129,
      "learning_rate": 0.00019551024972069126,
      "loss": 0.9707,
      "step": 28
    },
    {
      "epoch": 0.14646464646464646,
      "grad_norm": 5.9609551429748535,
      "learning_rate": 0.00019500184348547042,
      "loss": 0.836,
      "step": 29
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 3.8186469078063965,
      "learning_rate": 0.0001944669091607919,
      "loss": 0.5745,
      "step": 30
    },
    {
      "epoch": 0.15656565656565657,
      "grad_norm": 5.649787902832031,
      "learning_rate": 0.0001939055961204478,
      "loss": 0.7483,
      "step": 31
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 4.508133411407471,
      "learning_rate": 0.00019331806110416027,
      "loss": 0.6995,
      "step": 32
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 4.908481597900391,
      "learning_rate": 0.00019270446817381377,
      "loss": 0.7196,
      "step": 33
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 4.158113479614258,
      "learning_rate": 0.00019206498866764288,
      "loss": 0.6385,
      "step": 34
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 4.135396957397461,
      "learning_rate": 0.00019139980115238827,
      "loss": 0.5442,
      "step": 35
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 6.943304061889648,
      "learning_rate": 0.00019070909137343408,
      "loss": 0.6735,
      "step": 36
    },
    {
      "epoch": 0.18686868686868688,
      "grad_norm": 6.049618721008301,
      "learning_rate": 0.0001899930522029408,
      "loss": 0.6369,
      "step": 37
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 6.0904765129089355,
      "learning_rate": 0.00018925188358598813,
      "loss": 0.5841,
      "step": 38
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 7.102921009063721,
      "learning_rate": 0.00018848579248474288,
      "loss": 0.7621,
      "step": 39
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 5.9253764152526855,
      "learning_rate": 0.00018769499282066717,
      "loss": 0.4632,
      "step": 40
    },
    {
      "epoch": 0.20707070707070707,
      "grad_norm": 4.437100887298584,
      "learning_rate": 0.00018687970541478364,
      "loss": 0.6724,
      "step": 41
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 6.763703346252441,
      "learning_rate": 0.00018604015792601396,
      "loss": 0.6199,
      "step": 42
    },
    {
      "epoch": 0.21717171717171718,
      "grad_norm": 5.612349033355713,
      "learning_rate": 0.0001851765847876076,
      "loss": 0.6586,
      "step": 43
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.9788243770599365,
      "learning_rate": 0.0001842892271416797,
      "loss": 0.5972,
      "step": 44
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 5.281522750854492,
      "learning_rate": 0.00018337833277187472,
      "loss": 0.4751,
      "step": 45
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 5.539302349090576,
      "learning_rate": 0.00018244415603417603,
      "loss": 0.8702,
      "step": 46
    },
    {
      "epoch": 0.23737373737373738,
      "grad_norm": 5.218169689178467,
      "learning_rate": 0.00018148695778588033,
      "loss": 0.6168,
      "step": 47
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 6.879281520843506,
      "learning_rate": 0.0001805070053127563,
      "loss": 1.0051,
      "step": 48
    },
    {
      "epoch": 0.2474747474747475,
      "grad_norm": 10.114307403564453,
      "learning_rate": 0.0001795045722544083,
      "loss": 1.2669,
      "step": 49
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 3.8979644775390625,
      "learning_rate": 0.0001784799385278661,
      "loss": 0.6218,
      "step": 50
    },
    {
      "epoch": 0.25252525252525254,
      "eval_loss": 0.4242745339870453,
      "eval_runtime": 3.567,
      "eval_samples_per_second": 23.549,
      "eval_steps_per_second": 11.775,
      "step": 50
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 3.872249126434326,
      "learning_rate": 0.00017743339024942135,
      "loss": 0.4782,
      "step": 51
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 6.721828460693359,
      "learning_rate": 0.00017636521965473323,
      "loss": 0.5957,
      "step": 52
    },
    {
      "epoch": 0.2676767676767677,
      "grad_norm": 3.2468855381011963,
      "learning_rate": 0.00017527572501722512,
      "loss": 0.4427,
      "step": 53
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 6.151036739349365,
      "learning_rate": 0.00017416521056479577,
      "loss": 0.6467,
      "step": 54
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 3.0814287662506104,
      "learning_rate": 0.00017303398639486695,
      "loss": 0.424,
      "step": 55
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 3.6994075775146484,
      "learning_rate": 0.00017188236838779295,
      "loss": 0.4289,
      "step": 56
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 3.1827280521392822,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.4891,
      "step": 57
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 3.8212890625,
      "learning_rate": 0.00016951924276746425,
      "loss": 0.4761,
      "step": 58
    },
    {
      "epoch": 0.29797979797979796,
      "grad_norm": 5.331762313842773,
      "learning_rate": 0.0001683083950278031,
      "loss": 0.7219,
      "step": 59
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 4.787637710571289,
      "learning_rate": 0.00016707847301392236,
      "loss": 0.5826,
      "step": 60
    },
    {
      "epoch": 0.30808080808080807,
      "grad_norm": 3.337291717529297,
      "learning_rate": 0.00016582982016632818,
      "loss": 0.4699,
      "step": 61
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 4.400173664093018,
      "learning_rate": 0.00016456278515588024,
      "loss": 0.5866,
      "step": 62
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 4.839149475097656,
      "learning_rate": 0.00016327772178642986,
      "loss": 0.5345,
      "step": 63
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 4.648171424865723,
      "learning_rate": 0.00016197498889602448,
      "loss": 0.4628,
      "step": 64
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 4.890129566192627,
      "learning_rate": 0.00016065495025670675,
      "loss": 0.4923,
      "step": 65
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 5.739225387573242,
      "learning_rate": 0.00015931797447293552,
      "loss": 0.4155,
      "step": 66
    },
    {
      "epoch": 0.3383838383838384,
      "grad_norm": 3.6940314769744873,
      "learning_rate": 0.00015796443487865776,
      "loss": 0.3751,
      "step": 67
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 5.0201897621154785,
      "learning_rate": 0.00015659470943305955,
      "loss": 0.7349,
      "step": 68
    },
    {
      "epoch": 0.3484848484848485,
      "grad_norm": 12.40092945098877,
      "learning_rate": 0.00015520918061502569,
      "loss": 0.5633,
      "step": 69
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 4.143780708312988,
      "learning_rate": 0.00015380823531633729,
      "loss": 0.398,
      "step": 70
    },
    {
      "epoch": 0.35858585858585856,
      "grad_norm": 2.939042806625366,
      "learning_rate": 0.00015239226473363687,
      "loss": 0.4006,
      "step": 71
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 3.6455743312835693,
      "learning_rate": 0.00015096166425919175,
      "loss": 0.4675,
      "step": 72
    },
    {
      "epoch": 0.3686868686868687,
      "grad_norm": 5.916496753692627,
      "learning_rate": 0.00014951683337048537,
      "loss": 0.5441,
      "step": 73
    },
    {
      "epoch": 0.37373737373737376,
      "grad_norm": 3.209315538406372,
      "learning_rate": 0.00014805817551866838,
      "loss": 0.415,
      "step": 74
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 4.841739177703857,
      "learning_rate": 0.00014658609801589982,
      "loss": 0.4491,
      "step": 75
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 3.982872486114502,
      "learning_rate": 0.00014510101192161018,
      "loss": 0.5956,
      "step": 76
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 6.335887908935547,
      "learning_rate": 0.0001436033319277183,
      "loss": 0.4084,
      "step": 77
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 3.797659158706665,
      "learning_rate": 0.0001420934762428335,
      "loss": 0.4543,
      "step": 78
    },
    {
      "epoch": 0.398989898989899,
      "grad_norm": 4.0098371505737305,
      "learning_rate": 0.0001405718664754764,
      "loss": 0.3701,
      "step": 79
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 7.026660919189453,
      "learning_rate": 0.00013903892751634947,
      "loss": 0.5162,
      "step": 80
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 3.648876428604126,
      "learning_rate": 0.00013749508741969213,
      "loss": 0.5147,
      "step": 81
    },
    {
      "epoch": 0.41414141414141414,
      "grad_norm": 3.6191329956054688,
      "learning_rate": 0.00013594077728375128,
      "loss": 0.5438,
      "step": 82
    },
    {
      "epoch": 0.41919191919191917,
      "grad_norm": 4.088906764984131,
      "learning_rate": 0.00013437643113040301,
      "loss": 0.5964,
      "step": 83
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 8.929344177246094,
      "learning_rate": 0.0001328024857839569,
      "loss": 0.5646,
      "step": 84
    },
    {
      "epoch": 0.4292929292929293,
      "grad_norm": 5.202868938446045,
      "learning_rate": 0.00013121938074917865,
      "loss": 0.4918,
      "step": 85
    },
    {
      "epoch": 0.43434343434343436,
      "grad_norm": 3.181509017944336,
      "learning_rate": 0.00012962755808856342,
      "loss": 0.3981,
      "step": 86
    },
    {
      "epoch": 0.4393939393939394,
      "grad_norm": 3.2053065299987793,
      "learning_rate": 0.00012802746229889563,
      "loss": 0.4315,
      "step": 87
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 4.359558582305908,
      "learning_rate": 0.00012641954018712863,
      "loss": 0.5865,
      "step": 88
    },
    {
      "epoch": 0.4494949494949495,
      "grad_norm": 3.2212414741516113,
      "learning_rate": 0.00012480424074561933,
      "loss": 0.4918,
      "step": 89
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 4.372662544250488,
      "learning_rate": 0.00012318201502675285,
      "loss": 0.5305,
      "step": 90
    },
    {
      "epoch": 0.4595959595959596,
      "grad_norm": 3.6455907821655273,
      "learning_rate": 0.00012155331601699136,
      "loss": 0.44,
      "step": 91
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 5.014353275299072,
      "learning_rate": 0.0001199185985103836,
      "loss": 0.541,
      "step": 92
    },
    {
      "epoch": 0.4696969696969697,
      "grad_norm": 5.485827922821045,
      "learning_rate": 0.00011827831898156905,
      "loss": 0.572,
      "step": 93
    },
    {
      "epoch": 0.47474747474747475,
      "grad_norm": 4.1488142013549805,
      "learning_rate": 0.00011663293545831302,
      "loss": 0.5169,
      "step": 94
    },
    {
      "epoch": 0.4797979797979798,
      "grad_norm": 8.007122039794922,
      "learning_rate": 0.00011498290739360815,
      "loss": 0.6121,
      "step": 95
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 3.9420671463012695,
      "learning_rate": 0.0001133286955373779,
      "loss": 0.7262,
      "step": 96
    },
    {
      "epoch": 0.4898989898989899,
      "grad_norm": 3.958376884460449,
      "learning_rate": 0.00011167076180781764,
      "loss": 0.6058,
      "step": 97
    },
    {
      "epoch": 0.494949494949495,
      "grad_norm": 3.4940686225891113,
      "learning_rate": 0.00011000956916240985,
      "loss": 0.6586,
      "step": 98
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.9920654296875,
      "learning_rate": 0.000108345581468649,
      "loss": 0.4879,
      "step": 99
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 3.2610297203063965,
      "learning_rate": 0.00010667926337451217,
      "loss": 0.6111,
      "step": 100
    },
    {
      "epoch": 0.5050505050505051,
      "eval_loss": 0.3368319869041443,
      "eval_runtime": 3.6553,
      "eval_samples_per_second": 22.98,
      "eval_steps_per_second": 11.49,
      "step": 100
    },
    {
      "epoch": 0.51010101010101,
      "grad_norm": 3.021899700164795,
      "learning_rate": 0.00010501108017871192,
      "loss": 0.4974,
      "step": 101
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 2.496744394302368,
      "learning_rate": 0.00010334149770076747,
      "loss": 0.3512,
      "step": 102
    },
    {
      "epoch": 0.5202020202020202,
      "grad_norm": 2.980278968811035,
      "learning_rate": 0.00010167098215093009,
      "loss": 0.4924,
      "step": 103
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 2.7636165618896484,
      "learning_rate": 0.0001,
      "loss": 0.4474,
      "step": 104
    },
    {
      "epoch": 0.5303030303030303,
      "grad_norm": 2.929633617401123,
      "learning_rate": 9.83290178490699e-05,
      "loss": 0.4936,
      "step": 105
    },
    {
      "epoch": 0.5353535353535354,
      "grad_norm": 3.16523814201355,
      "learning_rate": 9.665850229923258e-05,
      "loss": 0.4352,
      "step": 106
    },
    {
      "epoch": 0.5404040404040404,
      "grad_norm": 2.280992031097412,
      "learning_rate": 9.498891982128809e-05,
      "loss": 0.3441,
      "step": 107
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 3.0064501762390137,
      "learning_rate": 9.332073662548784e-05,
      "loss": 0.3647,
      "step": 108
    },
    {
      "epoch": 0.5505050505050505,
      "grad_norm": 4.976753234863281,
      "learning_rate": 9.165441853135104e-05,
      "loss": 0.5351,
      "step": 109
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 4.739212512969971,
      "learning_rate": 8.999043083759017e-05,
      "loss": 0.3871,
      "step": 110
    },
    {
      "epoch": 0.5606060606060606,
      "grad_norm": 2.8724653720855713,
      "learning_rate": 8.832923819218238e-05,
      "loss": 0.3666,
      "step": 111
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 2.9768285751342773,
      "learning_rate": 8.667130446262214e-05,
      "loss": 0.3277,
      "step": 112
    },
    {
      "epoch": 0.5707070707070707,
      "grad_norm": 2.862802743911743,
      "learning_rate": 8.501709260639186e-05,
      "loss": 0.4887,
      "step": 113
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 2.7004799842834473,
      "learning_rate": 8.336706454168701e-05,
      "loss": 0.4897,
      "step": 114
    },
    {
      "epoch": 0.5808080808080808,
      "grad_norm": 3.854978322982788,
      "learning_rate": 8.172168101843099e-05,
      "loss": 0.4098,
      "step": 115
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 4.921027660369873,
      "learning_rate": 8.008140148961641e-05,
      "loss": 0.4852,
      "step": 116
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 5.069808006286621,
      "learning_rate": 7.844668398300865e-05,
      "loss": 0.5763,
      "step": 117
    },
    {
      "epoch": 0.5959595959595959,
      "grad_norm": 3.6147420406341553,
      "learning_rate": 7.681798497324716e-05,
      "loss": 0.4496,
      "step": 118
    },
    {
      "epoch": 0.601010101010101,
      "grad_norm": 2.794796943664551,
      "learning_rate": 7.519575925438067e-05,
      "loss": 0.4001,
      "step": 119
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.758659839630127,
      "learning_rate": 7.358045981287141e-05,
      "loss": 0.4717,
      "step": 120
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 3.865060567855835,
      "learning_rate": 7.197253770110438e-05,
      "loss": 0.4331,
      "step": 121
    },
    {
      "epoch": 0.6161616161616161,
      "grad_norm": 5.683581829071045,
      "learning_rate": 7.037244191143661e-05,
      "loss": 0.6139,
      "step": 122
    },
    {
      "epoch": 0.6212121212121212,
      "grad_norm": 4.08438777923584,
      "learning_rate": 6.878061925082137e-05,
      "loss": 0.4814,
      "step": 123
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 3.0704259872436523,
      "learning_rate": 6.719751421604309e-05,
      "loss": 0.4419,
      "step": 124
    },
    {
      "epoch": 0.6313131313131313,
      "grad_norm": 3.660254716873169,
      "learning_rate": 6.562356886959704e-05,
      "loss": 0.3549,
      "step": 125
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 2.445793390274048,
      "learning_rate": 6.405922271624874e-05,
      "loss": 0.2899,
      "step": 126
    },
    {
      "epoch": 0.6414141414141414,
      "grad_norm": 4.854302406311035,
      "learning_rate": 6.250491258030791e-05,
      "loss": 0.4754,
      "step": 127
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 5.60493278503418,
      "learning_rate": 6.0961072483650526e-05,
      "loss": 0.5704,
      "step": 128
    },
    {
      "epoch": 0.6515151515151515,
      "grad_norm": 2.915738582611084,
      "learning_rate": 5.9428133524523646e-05,
      "loss": 0.3904,
      "step": 129
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 2.7463226318359375,
      "learning_rate": 5.790652375716652e-05,
      "loss": 0.3646,
      "step": 130
    },
    {
      "epoch": 0.6616161616161617,
      "grad_norm": 3.881415367126465,
      "learning_rate": 5.639666807228175e-05,
      "loss": 0.5518,
      "step": 131
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 4.60642147064209,
      "learning_rate": 5.48989880783898e-05,
      "loss": 0.5252,
      "step": 132
    },
    {
      "epoch": 0.6717171717171717,
      "grad_norm": 3.854835271835327,
      "learning_rate": 5.341390198410019e-05,
      "loss": 0.3808,
      "step": 133
    },
    {
      "epoch": 0.6767676767676768,
      "grad_norm": 11.817362785339355,
      "learning_rate": 5.1941824481331626e-05,
      "loss": 0.5018,
      "step": 134
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 3.617809295654297,
      "learning_rate": 5.0483166629514654e-05,
      "loss": 0.4905,
      "step": 135
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 3.170531988143921,
      "learning_rate": 4.903833574080825e-05,
      "loss": 0.3767,
      "step": 136
    },
    {
      "epoch": 0.6919191919191919,
      "grad_norm": 3.8473992347717285,
      "learning_rate": 4.760773526636315e-05,
      "loss": 0.6115,
      "step": 137
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 2.3752405643463135,
      "learning_rate": 4.6191764683662744e-05,
      "loss": 0.2548,
      "step": 138
    },
    {
      "epoch": 0.702020202020202,
      "grad_norm": 3.695263385772705,
      "learning_rate": 4.479081938497435e-05,
      "loss": 0.5043,
      "step": 139
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 5.026264667510986,
      "learning_rate": 4.340529056694047e-05,
      "loss": 0.557,
      "step": 140
    },
    {
      "epoch": 0.7121212121212122,
      "grad_norm": 2.4456329345703125,
      "learning_rate": 4.2035565121342246e-05,
      "loss": 0.2723,
      "step": 141
    },
    {
      "epoch": 0.7171717171717171,
      "grad_norm": 3.4511559009552,
      "learning_rate": 4.0682025527064486e-05,
      "loss": 0.4311,
      "step": 142
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 4.066995143890381,
      "learning_rate": 3.934504974329326e-05,
      "loss": 0.5243,
      "step": 143
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.148977756500244,
      "learning_rate": 3.802501110397553e-05,
      "loss": 0.5212,
      "step": 144
    },
    {
      "epoch": 0.7323232323232324,
      "grad_norm": 5.859545707702637,
      "learning_rate": 3.672227821357014e-05,
      "loss": 0.6435,
      "step": 145
    },
    {
      "epoch": 0.7373737373737373,
      "grad_norm": 4.6083269119262695,
      "learning_rate": 3.543721484411976e-05,
      "loss": 0.4616,
      "step": 146
    },
    {
      "epoch": 0.7424242424242424,
      "grad_norm": 5.044768810272217,
      "learning_rate": 3.4170179833671846e-05,
      "loss": 0.6357,
      "step": 147
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 5.2436017990112305,
      "learning_rate": 3.292152698607768e-05,
      "loss": 0.3768,
      "step": 148
    },
    {
      "epoch": 0.7525252525252525,
      "grad_norm": 2.7868528366088867,
      "learning_rate": 3.169160497219692e-05,
      "loss": 0.4205,
      "step": 149
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 2.97955584526062,
      "learning_rate": 3.0480757232535772e-05,
      "loss": 0.3996,
      "step": 150
    },
    {
      "epoch": 0.7575757575757576,
      "eval_loss": 0.30316033959388733,
      "eval_runtime": 4.1074,
      "eval_samples_per_second": 20.451,
      "eval_steps_per_second": 10.226,
      "step": 150
    },
    {
      "epoch": 0.7626262626262627,
      "grad_norm": 2.366481065750122,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.2953,
      "step": 151
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 3.730241060256958,
      "learning_rate": 2.8117631612207084e-05,
      "loss": 0.4098,
      "step": 152
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 2.2350785732269287,
      "learning_rate": 2.6966013605133088e-05,
      "loss": 0.2896,
      "step": 153
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 2.9369983673095703,
      "learning_rate": 2.5834789435204243e-05,
      "loss": 0.3145,
      "step": 154
    },
    {
      "epoch": 0.7828282828282829,
      "grad_norm": 3.163738250732422,
      "learning_rate": 2.4724274982774865e-05,
      "loss": 0.3906,
      "step": 155
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 2.7925214767456055,
      "learning_rate": 2.3634780345266806e-05,
      "loss": 0.3608,
      "step": 156
    },
    {
      "epoch": 0.7929292929292929,
      "grad_norm": 3.376718759536743,
      "learning_rate": 2.2566609750578673e-05,
      "loss": 0.4218,
      "step": 157
    },
    {
      "epoch": 0.797979797979798,
      "grad_norm": 2.3512237071990967,
      "learning_rate": 2.1520061472133902e-05,
      "loss": 0.2628,
      "step": 158
    },
    {
      "epoch": 0.803030303030303,
      "grad_norm": 2.5450823307037354,
      "learning_rate": 2.04954277455917e-05,
      "loss": 0.3445,
      "step": 159
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 3.389965057373047,
      "learning_rate": 1.9492994687243714e-05,
      "loss": 0.3595,
      "step": 160
    },
    {
      "epoch": 0.8131313131313131,
      "grad_norm": 3.8269174098968506,
      "learning_rate": 1.851304221411967e-05,
      "loss": 0.4399,
      "step": 161
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 3.3702986240386963,
      "learning_rate": 1.7555843965823992e-05,
      "loss": 0.4206,
      "step": 162
    },
    {
      "epoch": 0.8232323232323232,
      "grad_norm": 4.068515300750732,
      "learning_rate": 1.6621667228125302e-05,
      "loss": 0.4435,
      "step": 163
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 3.2460782527923584,
      "learning_rate": 1.57107728583203e-05,
      "loss": 0.3687,
      "step": 164
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 3.4895899295806885,
      "learning_rate": 1.4823415212392377e-05,
      "loss": 0.3173,
      "step": 165
    },
    {
      "epoch": 0.8383838383838383,
      "grad_norm": 2.449981212615967,
      "learning_rate": 1.3959842073986085e-05,
      "loss": 0.2746,
      "step": 166
    },
    {
      "epoch": 0.8434343434343434,
      "grad_norm": 2.9149022102355957,
      "learning_rate": 1.3120294585216353e-05,
      "loss": 0.3383,
      "step": 167
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 2.762901544570923,
      "learning_rate": 1.230500717933285e-05,
      "loss": 0.3457,
      "step": 168
    },
    {
      "epoch": 0.8535353535353535,
      "grad_norm": 5.294210433959961,
      "learning_rate": 1.1514207515257147e-05,
      "loss": 0.2825,
      "step": 169
    },
    {
      "epoch": 0.8585858585858586,
      "grad_norm": 2.68806791305542,
      "learning_rate": 1.0748116414011888e-05,
      "loss": 0.2552,
      "step": 170
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 2.7005255222320557,
      "learning_rate": 1.0006947797059219e-05,
      "loss": 0.3095,
      "step": 171
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 3.141300678253174,
      "learning_rate": 9.29090862656593e-06,
      "loss": 0.409,
      "step": 172
    },
    {
      "epoch": 0.8737373737373737,
      "grad_norm": 2.8109939098358154,
      "learning_rate": 8.600198847611729e-06,
      "loss": 0.2594,
      "step": 173
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 4.259993553161621,
      "learning_rate": 7.935011332357112e-06,
      "loss": 0.38,
      "step": 174
    },
    {
      "epoch": 0.8838383838383839,
      "grad_norm": 3.043079137802124,
      "learning_rate": 7.295531826186264e-06,
      "loss": 0.3713,
      "step": 175
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 4.630237579345703,
      "learning_rate": 6.681938895839746e-06,
      "loss": 0.383,
      "step": 176
    },
    {
      "epoch": 0.8939393939393939,
      "grad_norm": 2.737017869949341,
      "learning_rate": 6.094403879552213e-06,
      "loss": 0.2805,
      "step": 177
    },
    {
      "epoch": 0.898989898989899,
      "grad_norm": 4.985474109649658,
      "learning_rate": 5.533090839208133e-06,
      "loss": 0.3841,
      "step": 178
    },
    {
      "epoch": 0.9040404040404041,
      "grad_norm": 6.950056076049805,
      "learning_rate": 4.998156514529595e-06,
      "loss": 0.4571,
      "step": 179
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 4.946906089782715,
      "learning_rate": 4.489750279308757e-06,
      "loss": 0.347,
      "step": 180
    },
    {
      "epoch": 0.9141414141414141,
      "grad_norm": 3.9695048332214355,
      "learning_rate": 4.008014099696922e-06,
      "loss": 0.5263,
      "step": 181
    },
    {
      "epoch": 0.9191919191919192,
      "grad_norm": 8.271167755126953,
      "learning_rate": 3.5530824945623542e-06,
      "loss": 0.4697,
      "step": 182
    },
    {
      "epoch": 0.9242424242424242,
      "grad_norm": 4.283810615539551,
      "learning_rate": 3.1250824979274675e-06,
      "loss": 0.3751,
      "step": 183
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 4.335268497467041,
      "learning_rate": 2.7241336234962944e-06,
      "loss": 0.4739,
      "step": 184
    },
    {
      "epoch": 0.9343434343434344,
      "grad_norm": 2.71360445022583,
      "learning_rate": 2.3503478312815298e-06,
      "loss": 0.3239,
      "step": 185
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 3.5677242279052734,
      "learning_rate": 2.003829496341325e-06,
      "loss": 0.3414,
      "step": 186
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 4.159941673278809,
      "learning_rate": 1.684675379633649e-06,
      "loss": 0.4585,
      "step": 187
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 2.4791529178619385,
      "learning_rate": 1.3929746009971433e-06,
      "loss": 0.2787,
      "step": 188
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 3.9080071449279785,
      "learning_rate": 1.1288086142653864e-06,
      "loss": 0.4613,
      "step": 189
    },
    {
      "epoch": 0.9595959595959596,
      "grad_norm": 2.8919191360473633,
      "learning_rate": 8.922511845219971e-07,
      "loss": 0.3061,
      "step": 190
    },
    {
      "epoch": 0.9646464646464646,
      "grad_norm": 3.1575520038604736,
      "learning_rate": 6.833683675025904e-07,
      "loss": 0.385,
      "step": 191
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 2.799712896347046,
      "learning_rate": 5.022184911495864e-07,
      "loss": 0.2826,
      "step": 192
    },
    {
      "epoch": 0.9747474747474747,
      "grad_norm": 4.0444159507751465,
      "learning_rate": 3.488521393248401e-07,
      "loss": 0.3397,
      "step": 193
    },
    {
      "epoch": 0.9797979797979798,
      "grad_norm": 3.229677200317383,
      "learning_rate": 2.2331213768468363e-07,
      "loss": 0.464,
      "step": 194
    },
    {
      "epoch": 0.9848484848484849,
      "grad_norm": 5.421383857727051,
      "learning_rate": 1.2563354172142606e-07,
      "loss": 0.4543,
      "step": 195
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 8.108620643615723,
      "learning_rate": 5.584362697453882e-08,
      "loss": 0.5336,
      "step": 196
    },
    {
      "epoch": 0.9949494949494949,
      "grad_norm": 3.2131192684173584,
      "learning_rate": 1.3961881414292778e-08,
      "loss": 0.4028,
      "step": 197
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.490635395050049,
      "learning_rate": 0.0,
      "loss": 0.4676,
      "step": 198
    }
  ],
  "logging_steps": 1,
  "max_steps": 198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.812060362394829e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}